Copertina

RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Mao, Yixiu, Qu, Yun, Wang, Qi, Zou, Heming, Ji, Xiangyang
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models
di: Mao, Yixiu, et al.
Pubblicazione: (2026)

Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex
di: Qu, Yun, et al.
Pubblicazione: (2026)

Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning
di: Zou, Heming, et al.
Pubblicazione: (2025)

Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning
di: Mao, Yixiu, et al.
Pubblicazione: (2025)

Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments
di: Qu, Yun, et al.
Pubblicazione: (2025)

Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression
di: Mao, Yixiu, et al.
Pubblicazione: (2024)

Doubly Mild Generalization for Offline Reinforcement Learning
di: Mao, Yixiu, et al.
Pubblicazione: (2024)

Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?
di: Qu, Yun, et al.
Pubblicazione: (2025)

Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models
di: Qu, Yun, et al.
Pubblicazione: (2026)

Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning
di: Qu, Yun, et al.
Pubblicazione: (2024)

VAO: Validation-Aligned Optimization for Cross-Task Generative Auto-Bidding
di: Lv, Yiqin, et al.
Pubblicazione: (2025)

On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation
di: Huang, Kexin, et al.
Pubblicazione: (2026)

Quantile Advantage Estimation: Stabilizing RLVR for LLM Reasoning
di: Wu, Junkang, et al.
Pubblicazione: (2025)

Structural features of the fly olfactory circuit mitigate the stability-plasticity dilemma in continual learning
di: Zou, Heming, et al.
Pubblicazione: (2025)

Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal Reasoning
di: Huang, Zhuoxu, et al.
Pubblicazione: (2026)

The Path Not Taken: RLVR Provably Learns Off the Principals
di: Zhu, Hanqing, et al.
Pubblicazione: (2025)

Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration
di: Chen, Zhipeng, et al.
Pubblicazione: (2026)

Fly-CL: A Fly-Inspired Framework for Enhancing Efficient Decorrelation and Reduced Training Time in Pre-trained Model-based Continual Representation Learning
di: Zou, Heming, et al.
Pubblicazione: (2025)

Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration
di: Yang, Zhicheng, et al.
Pubblicazione: (2025)

FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts
di: Zou, Heming, et al.
Pubblicazione: (2025)

Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning
di: Wang, Ziyan, et al.
Pubblicazione: (2025)

Understanding and Preventing Entropy Collapse in RLVR with On-Policy Entropy Flow Optimization
di: Xu, Huimin, et al.
Pubblicazione: (2026)

RLPR: Extrapolating RLVR to General Domains without Verifiers
di: Yu, Tianyu, et al.
Pubblicazione: (2025)

Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
di: Li, Gengsheng, et al.
Pubblicazione: (2026)

Learning to Reason under Off-Policy Guidance
di: Yan, Jianhao, et al.
Pubblicazione: (2025)

Model Predictive Task Sampling for Efficient and Robust Adaptation
di: Wang, Qi, et al.
Pubblicazione: (2025)

Adaptive Negative Reinforcement for LLM Reasoning:Dynamically Balancing Correction and Diversity in RLVR
di: Ingle, Yash, et al.
Pubblicazione: (2026)

CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR
di: Cui, Sijia, et al.
Pubblicazione: (2026)

Group-in-Group Policy Optimization for LLM Agent Training
di: Feng, Lang, et al.
Pubblicazione: (2025)

Shorter but not Worse: Frugal Reasoning via Easy Samples as Length Regularizers in Math RLVR
di: Bounhar, Abdelaziz, et al.
Pubblicazione: (2025)

When to Stop Reusing: Dynamic Gradient Gating for Sample-Efficient RLVR
di: Miao, Yuchun, et al.
Pubblicazione: (2026)

Unearthing Gems from Stones: Policy Optimization with Negative Sample Augmentation for LLM Reasoning
di: Yang, Zhaohui, et al.
Pubblicazione: (2025)

VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
di: Shen, Guobin, et al.
Pubblicazione: (2026)

Structured Role-Aware Policy Optimization for Multimodal Reasoning
di: Jiang, Bingqing, et al.
Pubblicazione: (2026)

Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization
di: Wang, Junzhe, et al.
Pubblicazione: (2026)

Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
di: Liu, Zeyuan, et al.
Pubblicazione: (2026)

Hybrid Group Relative Policy Optimization: A Multi-Sample Approach to Enhancing Policy Optimization
di: Sane, Soham
Pubblicazione: (2025)

Group Orthogonalized Policy Optimization:Group Policy Optimization as Orthogonal Projection in Hilbert Space
di: Zixian, Wang
Pubblicazione: (2026)

Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning
di: Zhang, Xichen, et al.
Pubblicazione: (2025)

Detector-Evasive LLM Paraphrasing via Constrained Policy Optimization
di: Wang, Mingyi, et al.
Pubblicazione: (2026)